Ziniu Li

Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward

TreePO: Enhancing Policy Efficacy and Inference Efficiency with Tree Modeling

SpeechJudge: Towards Human-Level Judgment for Speech Naturalness

Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation

Bridging Formal Language with Chain-of-Thought Reasoning to Geometry Problem Solving

ORGEval: Graph-Theoretic Evaluation of LLMs in Optimization Modeling

Stepwise Guided Policy Optimization: Coloring your Incorrect Reasoning in GRPO

Long CoT In-Context Learning Can Empower Pre-trained LLMs

Understanding and Mitigating Hallucination in Large Vision-Language Models via Modular Attribution and Intervention

Adam-mini: Use Fewer Learning Rates To Gain More

Teaching Language Models to Reason with Tools

Self-Evolving Critique Abilities in Large Language Models

Preserving Diversity in Supervised Fine-Tuning of Large Language Models

Controlling Large Language Model with Latent Action